Image Hashing based on Shape Context and Speeded Up Robust Features (SURF)

Image Authentication is one of the key issue in today’s age of multimedia technology. With the availability of many hacking techniques and picture editing tools like Photoshop, image security is a major research field. Local feature points are elaborately used in resolving many problems, i.e., object detection, robust matching etc., but its use in the field of image hashing is not explored. In this work, we propose image hashing based on shape-context via Speeded Up Robust Features (SURF). The work is motivated by SIFT-based approach. Our contributions are: 1) SURF based algorithm is several times faster than SIFT-based algorithm. 2) It is more robust against different type of image modifications than SIFT. 3) We have incorporated rotation invariance property. Rotation is a difficult content preserving operation to model. The experiments are carried out on 1000 images and have shown that the proposed image hashing technique is robust against content-preserving operations. The region of convergence shows the efficacy of the proposed method compared to many state-of-the-art methods.

[1]  Xuelong Li,et al.  Latent Semantic Minimal Hashing for Image Retrieval , 2017, IEEE Transactions on Image Processing.

[2]  Zhenjun Tang,et al.  Perceptual Image Hashing with Weighted DWT Features for Reduced-Reference Image Quality Assessment , 2018, Comput. J..

[3]  Mohammed Yakoob Siyal,et al.  A secure and robust hash-based scheme for image authentication , 2010, Signal Process..

[4]  Ram Kumar Karsh,et al.  Robust image hashing using ring partition-PGNMF and local features , 2016, SpringerPlus.

[5]  R. Varatharajan,et al.  Whirlpool Algorithm with Hash Function Based Watermarking Algorithm for the Secured Transmission of Digital Medical Images , 2018 .

[6]  Zhenjun Tang,et al.  Perceptual Hashing for Color Images Using Invariant Moments , 2012 .

[7]  Ram Kumar Karsh,et al.  Perceptual robust and secure image hashing using ring partition-PGNMF , 2015, TENCON 2015 - 2015 IEEE Region 10 Conference.

[8]  Aditi,et al.  Robust image hashing through DWT-SVD and spectral residual method , 2017, EURASIP Journal on Image and Video Processing.

[9]  Z. Jane Wang,et al.  Perceptual Image Hashing Based on Shape Contexts and Local Feature Points , 2012, IEEE Transactions on Information Forensics and Security.

[10]  Xinpeng Zhang,et al.  Lexicographical framework for image hashing with implementation based on DCT and NMF , 2009, Multimedia Tools and Applications.

[11]  Jitendra Malik,et al.  Shape matching and object recognition using shape contexts , 2010, 2010 3rd International Conference on Computer Science and Information Technology.

[12]  Shichao Zhang,et al.  Robust Image Hashing With Ring Partition and Invariant Vector Distance , 2016, IEEE Transactions on Information Forensics and Security.

[13]  Zhenjun Tang,et al.  Robust image hashing using ring-based entropies , 2013, Signal Process..

[14]  Rabul Hussain Laskar,et al.  Image authentication based on robust image hashing with geometric correction , 2018, Multimedia Tools and Applications.

[15]  Xinpeng Zhang,et al.  Robust Image Hashing for Tamper Detection Using Non-Negative Matrix Factorization , 2008 .

[16]  Ram Kumar Karsh,et al.  Image authentication under geometric attacks via concentric square partition based image hashing , 2017, TENCON 2017 - 2017 IEEE Region 10 Conference.

[17]  Shichao Zhang,et al.  Robust Perceptual Image Hashing Based on Ring Partition and NMF , 2014, IEEE Transactions on Knowledge and Data Engineering.